SI-ADMM: A stochastic inexact admm framework for resolving structured stochastic convex programs

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

We consider the resolution of the structured stochastic convex program: min E[ f (x;x )]+E[ g(y;x )] such that Ax+By =b. To exploit problem structure and allow for developing distributed schemes, we propose an inexact stochastic generalization in which the subproblems are solved inexactly via stochastic approximation schemes. Based on this framework, we prove the following: (i) when the inexactness sequence satisfies suitable summability properties, the proposed stochastic inexact ADMM (SI-ADMM) scheme produces a sequence that converges to the unique solution almost surely; (ii) if the inexactness is driven to zero at a polynomial (geometric) rate, the sequence converges to the unique solution in a mean-squared sense at a prescribed polynomial (geometric) rate.

Original languageEnglish (US)
Title of host publication2016 Winter Simulation Conference
Subtitle of host publicationSimulating Complex Service Systems, WSC 2016
EditorsTheresa M. Roeder, Peter I. Frazier, Robert Szechtman, Enlu Zhou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages714-725
Number of pages12
ISBN (Electronic)9781509044863
DOIs
StatePublished - Jul 2 2016
Event2016 Winter Simulation Conference, WSC 2016 - Arlington, United States
Duration: Dec 11 2016Dec 14 2016

Publication series

NameProceedings - Winter Simulation Conference
Volume0
ISSN (Print)0891-7736

Other

Other2016 Winter Simulation Conference, WSC 2016
CountryUnited States
CityArlington
Period12/11/1612/14/16

All Science Journal Classification (ASJC) codes

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Fingerprint Dive into the research topics of 'SI-ADMM: A stochastic inexact admm framework for resolving structured stochastic convex programs'. Together they form a unique fingerprint.

Cite this